AI is helping scientists develop lifechanging materials of the future

Nylon, Teflon, and Kevlar are just a few examples of polymers—large-molecule chemical compounds—that have revolutionized the world. These materials, found in everything from non-stick frying pans to the realm of 3D printing, are essential in the creation of technologies that enhance everyday life.

The challenge of discovering the next groundbreaking polymer is immense, but researchers at Georgia Tech are turning to artificial intelligence (AI) to help shape the future of this field. Rampi Ramprasad’s group is at the forefront of this effort, using AI algorithms to accelerate the discovery of new materials.

This summer, two papers published in the prestigious Nature family of journals highlighted significant advancements and success stories from years of AI-driven research in polymer informatics. The first paper, featured in Nature Reviews Materials, outlines recent breakthroughs in polymer design, focusing on applications like energy storage, filtration technologies, and recyclable plastics.

The second paper, published in Nature Communications, delves into how AI algorithms were used to discover a subclass of polymers specifically for electrostatic energy storage. The designed materials underwent successful laboratory synthesis and testing, marking a significant step forward.

“In the early days of AI in materials science, propelled by the White House’s Materials Genome Initiative over a decade ago, research in this field was largely curiosity-driven,” explained Ramprasad, a professor in the School of Materials Science and Engineering.

“Only in recent years have we begun to see tangible, real-world success stories in AI-driven accelerated polymer discovery. These successes are now inspiring significant transformations in the industrial materials R&D landscape. That’s what makes this review so significant and timely,” Ramprasad continued.

Ramprasad’s team has developed innovative algorithms capable of predicting polymer properties and formulations instantly, before they are even physically created. The process starts by identifying specific target properties or performance criteria for a given application.

Machine learning (ML) models are then trained on existing material-property data to predict these desired outcomes. Additionally, the team can generate new polymers, with their properties forecasted using ML models. The most promising candidates that meet the target property criteria are selected for real-world validation through laboratory synthesis and testing. The results from these experiments are then fed back into the system, continuously refining the predictive models in an iterative process.

While AI holds the potential to accelerate the discovery of new polymers, it also comes with its own set of challenges. The accuracy of AI predictions hinges on the availability of rich, diverse, and extensive data sets, making quality data crucial. Moreover, designing algorithms that can generate chemically realistic and synthesizable polymers is a complex task.

The real test begins after the algorithms make their predictions: proving that the designed materials can be synthesized in the lab, function as expected, and then demonstrating their scalability beyond the lab for real-world applications.

Ramprasad’s group focuses on designing these materials, while their fabrication, processing, and testing are carried out by collaborators at various institutions, including Georgia Tech. Professor Ryan Lively from the School of Chemical and Biomolecular Engineering is one such collaborator and a co-author of the Nature Reviews Materials paper.

"In our day-to-day research, we extensively use the machine learning models Rampi’s team has developed,” Lively noted. “These tools accelerate our work and allow us to rapidly explore new ideas. This embodies the promise of ML and AI because we can make model-guided decisions before we commit time and resources to explore the concepts in the laboratory."

Through the use of AI, Ramprasad’s team and their collaborators have made significant progress in various fields, including energy storage, filtration technologies, additive manufacturing, and recyclable materials.

One notable success, detailed in the Nature Communications paper, involves the design of new polymers for capacitors, which store electrostatic energy. These devices are critical components in electric and hybrid vehicles, among other applications. Ramprasad’s group worked with researchers from the University of Connecticut to achieve this breakthrough.

Current capacitor polymers typically offer either high energy density or thermal stability, but rarely both. By leveraging AI tools, the researchers discovered that insulating materials made from polynorbornene and polyimide polymers could simultaneously achieve high energy density and high thermal stability. These polymers can also be enhanced to function in demanding environments, such as aerospace applications, while maintaining environmental sustainability.

“The new class of polymers with high energy density and high thermal stability is one of the most concrete examples of how AI can guide materials discovery,” Ramprasad emphasized. “It is also the result of years of multidisciplinary collaborative work with Greg Sotzing and Yang Cao at the University of Connecticut and sustained sponsorship by the Office of Naval Research.”

The potential for real-world application of AI-assisted materials development is further highlighted by the involvement of industry in the Nature Reviews Materials article. Co-authors of this paper include scientists from the Toyota Research Institute and General Electric.

To accelerate the adoption of AI-driven materials development in industry, Ramprasad co-founded Matmerize Inc., a software startup recently spun out of Georgia Tech. Their cloud-based polymer informatics software is already being used by companies across various sectors, including energy, electronics, consumer products, chemical processing, and sustainable materials.

“Matmerize has transformed our research into a robust, versatile, and industry-ready solution, enabling users to design materials virtually with enhanced efficiency and reduced cost,” Ramprasad said. “What began as a curiosity has gained significant momentum, and we are entering an exciting new era of materials by design.”

Note: Materials provided above by The Brighter Side of News. Content may be edited for style and length.

Like these kind of feel good stories? Get The Brighter Side of News' newsletter.